Accelerate Federated Learning Model Deployment with KServe (KFServing)
Talkat KubeCon + CloudNativeCon + Open Source Summit China 2021 · on Thursday, 2021-12-09· at 13:15· Kubecon + CloudNativeCon 演讲厅, 虚拟会议 (Virtual)·
summary
The talk explains how KFServing (Kubeflow’s inference component) and KubeFATE (cloud‑native federated learning on Kubernetes) can be used together to serve federated learning models. It covers Kubeflow/KFServing and the InferenceService workflow, outlines federated learning fundamentals and algorithm/use‑case types, and demonstrates creating a KFServing deployment from a horizontally trained federated model.
AI-written summary · about
related talks
39mIntroducing KFServing: Serverless Model Serving on Kubernetes
21mWhat, Why and How of Federated Machine Learning – Implementation Using...
35mAdvanced Model Inferencing Leveraging KNative, Istio & Kubeflow Serving
37mAccelerate and Autoscale Deep Learning Inference on GPUs with KFServing
10mBuilding Machine Learning Inference Through Knative Serverless...
14mAI Deployment: Mastering LLMs with KFServing in Kubernetes
28mExploring ML Model Serving with KServe (with fun drawings)
35mServing Large Language Models using KServe